Search For:

Displaying 1-33 out of 33 total
Looking Beyond the Visible Scene
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Aditya Khosla,Byoungkwon An,Joseph J. Lim,Antonio Torralba
Issue Date:June 2014
pp. 3710-3717
A common thread that ties together many prior works in scene understanding is their focus on the aspects directly present in a scene such as its categorical classification or the set of objects. In this work, we propose to look beyond the visible elements ...
 
SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Jianxiong Xiao,Andrew Owens,Antonio Torralba
Issue Date:December 2013
pp. 1625-1632
Existing scene understanding datasets contain only a limited set of views of a place, and they lack representations of complete 3D spaces. In this paper, we introduce SUN3D, a large-scale RGB-D video database with camera pose and object labels, capturing t...
 
Modifying the Memorability of Face Photographs
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Aditya Khosla,Wilma A. Bainbridge,Antonio Torralba,Aude Oliva
Issue Date:December 2013
pp. 3200-3207
Contemporary life bombards us with many new images of faces every day, which poses non-trivial constraints on human memory. The vast majority of face photographs are intended to be remembered, either because of personal relevance, commercial interests or b...
 
HOGgles: Visualizing Object Detection Features
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Carl Vondrick,Aditya Khosla,Tomasz Malisiewicz,Antonio Torralba
Issue Date:December 2013
pp. 1-8
We introduce algorithms to visualize feature spaces used by object detectors. The tools in this paper allow a human to put on 'HOG goggles' and perceive the visual world as a HOG based object detector sees it. We found that these visualizations allow us to...
 
Parsing IKEA Objects: Fine Pose Estimation
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Joseph J. Lim,Hamed Pirsiavash,Antonio Torralba
Issue Date:December 2013
pp. 2992-2999
We address the problem of localizing and estimating the fine-pose of objects in the image with exact 3D models. Our main focus is to unify contributions from the 1970s with recent advances in object detection: use local keypoint detectors to find candidate...
 
Shape Anchors for Data-Driven Multi-view Reconstruction
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Andrew Owens,Jianxiong Xiao,Antonio Torralba,William Freeman
Issue Date:December 2013
pp. 33-40
We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their laten...
 
A Tree-Based Context Model for Object Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Myung Jin Choi,Antonio Torralba,Alan S. Willsky
Issue Date:February 2012
pp. 240-252
There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context model can rule out some unlikely combinations or locations of objects and guide de...
 
Evaluation of image features using a photorealistic virtual world
Found in: Computer Vision, IEEE International Conference on
By Biliana Kaneva,Antonio Torralba,William T. Freeman
Issue Date:November 2011
pp. 2282-2289
Image features are widely used in computer vision applications. They need to be robust to scene changes and image transformations. Designing and comparing feature descriptors requires the ability to evaluate their performance with respect to those transfor...
 
AVSS 2011 demo session: A large-scale benchmark dataset for event recognition in surveillance video
Found in: 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2011)
By Sangmin Oh,Anthony Hoogs,Amitha Perera,Naresh Cuntoor,Chia-Chih Chen,Jong Taek Lee,Saurajit Mukherjee,J. K. Aggarwal,Hyungtae Lee,Larry Davis,Eran Swears,Xiaoyang Wang,Qiang Ji,Kishore Reddy,Mubarak Shah,Carl Vondrick,Hamed Pirsiavash,Deva Ramanan,Jenny Yuen,Antonio Torralba,Bi Song,Anesco Fong,Amit Roy-Chowdhury,Mita Desai
Issue Date:August 2011
pp. 527-528
Summary form only given. We present a concept for automatic construction site monitoring by taking into account 4D information (3D over time), that is acquired from highly-overlapping digital aerial images. On the one hand today's maturity of flying micro ...
   
Nonparametric Scene Parsing via Label Transfer
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ce Liu,Jenny Yuen,Antonio Torralba
Issue Date:December 2011
pp. 2368-2382
While there has been a lot of recent work on object recognition and image understanding, the focus has been on carefully establishing mathematical models for images, scenes, and objects. In this paper, we propose a novel, nonparametric approach for object ...
 
SIFT Flow: Dense Correspondence across Scenes and Its Applications
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Ce Liu, Jenny Yuen, Antonio Torralba
Issue Date:May 2011
pp. 978-994
While image alignment has been studied in different areas of computer vision for decades, aligning images depicting different scenes remains a challenging problem. Analogous to optical flow, where an image is aligned to its temporally adjacent frame, we pr...
 
Part and appearance sharing: Recursive Compositional Models for multi-view
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Multi-Object Detection, Long (Leo) Zhu, Yuanhao Chen, Antonio Torralba, William Freeman, Alan Yuille
Issue Date:June 2010
pp. 1919-1926
We propose Recursive Compositional Models (RCMs) for simultaneous multi-view multi-object detection and parsing (e.g. view estimation and determining the positions of the object subparts). We represent the set of objects by a family of RCMs where each RCM ...
 
Exploiting hierarchical context on a large database of object categories
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Myung Jin Choi, Joseph J. Lim, Antonio Torralba, Alan S. Willsky
Issue Date:June 2010
pp. 129-136
There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. Context models can efficiently rule out some unlikely combinations or locations of objects a...
 
SUN database: Large-scale scene recognition from abbey to zoo
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jianxiong Xiao, James Hays, Krista A. Ehinger, Aude Oliva, Antonio Torralba
Issue Date:June 2010
pp. 3485-3492
Scene categorization is a fundamental problem in computer vision. However, scene understanding research has been constrained by the limited scope of currently-used databases which do not capture the full variety of scene categories. Whereas standard databa...
 
Guest Editors' Introduction to the Special Section on Probabilistic Graphical Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Qiang Ji, Jiebo Luo, Dimitris Metaxas, Antonio Torralba, Thomas S. Huang, Erik B. Sudderth
Issue Date:October 2009
pp. 1729-1732
No summary available.
 
Creating and exploring a large photorealistic virtual space
Found in: Computer Vision and Pattern Recognition Workshop
By Josef Sivic, Biliana Kaneva, Antonio Torralba, Shai Avidan, William T. Freeman
Issue Date:June 2008
pp. 1-8
We present a system for exploring large collections of photos in a virtual 3D space. Our system does not assume the photographs are of a single real 3D location, nor that they were taken at the same time. Instead, we organize the photos in themes, such as ...
 
Small codes and large image databases for recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Antonio Torralba, Rob Fergus, Yair Weiss
Issue Date:June 2008
pp. 1-8
The Internet contains billions of images, freely available online. Methods for efficiently searching this incredibly rich resource are vital for a large number of applications. These include object recognition [2], computer graphics [11, 27], personal phot...
 
Sharing Visual Features for Multiclass and Multiview Object Detection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Antonio Torralba, Kevin P. Murphy, William T. Freeman
Issue Date:May 2007
pp. 854-869
We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, at multiple locations and scales. This can be slow and can req...
 
Depth from Familiar Objects: A Hierarchical Model for 3D Scenes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Erik B. Sudderth, Antonio Torralba, William T. Freeman, Alan S. Willsky
Issue Date:June 2006
pp. 2410-2417
We develop an integrated, probabilistic model for the appearance and three-dimensional geometry of cluttered scenes. Object categories are modeled via distributions over the 3D location and appearance of visual features. Uncertainty in the number of object...
 
Learning Hierarchical Models of Scenes, Objects, and Parts
Found in: Computer Vision, IEEE International Conference on
By Erik B. Sudderth, Antonio Torralba, William T. Freeman, Alan S. Willsky
Issue Date:October 2005
pp. 1331-1338
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the expected appearance and position, in an object centered coordinate frame, of f...
 
Human Learning of Contextual Priors for Object Search: Where does the time go?
Found in: Computer Vision and Pattern Recognition Workshop
By Barbara Hidalgo-Sotelo, Aude Oliva, Antonio Torralba
Issue Date:June 2005
pp. 86
<p>Attention allocation in visual search is known to be influenced by low-level image features, visual scene context and top down task constraints. Here, we investigate the role of Contextual priors in guiding visual search by monitoring eye movement...
 
Sharing Features: Efficient Boosting Procedures for Multiclass Object Detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Antonio Torralba, Kevin P. Murphy, William T. Freeman
Issue Date:July 2004
pp. 762-769
We consider the problem of detecting a large number of different object classes in cluttered scenes. Traditional approaches require applying a battery of different classifiers to the image, which can be slow and require much training data. We present a mul...
 
Context-based vision system for place and object recognition
Found in: Computer Vision, IEEE International Conference on
By Antonio Torralba, Kevin P. Murphy, William T. Freeman, Mark A. Rubin
Issue Date:October 2003
pp. 273
While navigating in an environment, a vision system has to be able to recognize where it is and what the main objects in the scene are. In this paper we present a context-based vision system for place and object recognition. The goal is to identify familia...
 
Statistical Context Priming for Object Detection
Found in: Computer Vision, IEEE International Conference on
By Antonio Torralba, Pawan Sinha
Issue Date:July 2001
pp. 763
There is general consensus that context can be a rich source of information about an object?s identity, location and scale. However, the issue of how to formalize contextual influences is still largely open. Here we introduce a simple probabilistic framewo...
 
What Makes a Photograph Memorable?
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Phillip Isola,Jianxiong Xiao,Devi Parikh,Antonio Torralba,Aude Oliva
Issue Date:July 2014
pp. 1-1
When glancing at a magazine, or browsing the Internet, we are continuously exposed to photographs. Despite this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not ...
 
Unsupervised Non-parametric Geospatial Modeling from Ground Imagery
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Nathan Frey,Antonio Torralba,Christopher Stauffer
Issue Date:March 2014
pp. 698-705
Densely and regularly sampled ground-level imagery collected from semi-automated vehicle collection platforms (e.g. Street View TM or EarthMine TM ) is rapidly becoming available on a global scale. Ground level views of neighborhoods around the world can p...
   
What Makes a Photograph Memorable?
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Phillip Isola,Jianxiong Xiao,Devi Parikh,Antonio Torralba,Aude Oliva
Issue Date:October 2013
pp. 1
When glancing at a magazine, or browsing the Internet, we are continuously exposed to photographs. Despite this overflow of visual information, humans are extremely good at remembering thousands of pictures along with some of their visual details. But not ...
 
Properties and Applications of Shape Recipes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Antonio Torralba, William T. Freeman
Issue Date:June 2003
pp. 383
In low-level vision, the representations of scene properties such as shape, albedo, etc., are very high dimensional as they have to describe complicated structures. The approach proposed here is to let the image itself bear as much of the representational ...
 
Depth Estimation from Image Structure
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Antonio Torralba, Aude Oliva
Issue Date:September 2002
pp. 1226-1238
<p><b>Abstract</b>—In the absence of cues for absolute depth measurements as binocular disparity, motion, or defocus, the absolute distance between the observer and a scene cannot be measured. The interpretation of shading, edges, and jun...
 
Basic level scene understanding: from labels to structure and beyond
Found in: SIGGRAPH Asia 2012 Technical Briefs (SA '12)
By Antonio Torralba, Aude Oliva, Bryan C. Russell, James Hays, Jianxiong Xiao, Krista A. Ehinger
Issue Date:November 2012
pp. 1-4
An early goal of computer vision was to build a system that could automatically understand a 3D scene just by looking. This requires not only the ability to extract 3D information from image information alone, but also to handle the large variety of differ...
     
Image memorability and visual inception
Found in: SIGGRAPH Asia 2012 Technical Briefs (SA '12)
By Aditya Khosla, Antonio Torralba, Aude Oliva, Jianxiong Xiao, Phillip Isola
Issue Date:November 2012
pp. 1-4
When glancing at a magazine, or browsing the Internet, we are continuously being exposed to photographs. However, not all images are equal in memory; some stitch to our minds, while others are forgotten. In this paper we discuss the notion of image memorab...
     
Hybrid images: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: ACM SIGGRAPH 2006 Papers (SIGGRAPH '06)
By Antonio Torralba, Aude Oliva, Philippe. G. Schyns
Issue Date:July 2006
pp. 6-es
We present hybrid images, a technique that produces static images with two interpretations, which change as a function of viewing distance. Hybrid images are based on the multiscale processing of images by the human visual system and are motivated by maski...
     
Hybrid images: Copyright restrictions prevent ACM from providing the full text for this work.
Found in: Material presented at the ACM SIGGRAPH 2006 conference (SIGGRAPH '06)
By Antonio Torralba, Aude Oliva, Philippe. G. Schyns
Issue Date:July 2006
pp. 6-es
We present hybrid images, a technique that produces static images with two interpretations, which change as a function of viewing distance. Hybrid images are based on the multiscale processing of images by the human visual system and are motivated by maski...
     
 1